CN106162652A - A kind of base station location localization method based on drive test data - Google Patents
A kind of base station location localization method based on drive test data Download PDFInfo
- Publication number
- CN106162652A CN106162652A CN201610757586.5A CN201610757586A CN106162652A CN 106162652 A CN106162652 A CN 106162652A CN 201610757586 A CN201610757586 A CN 201610757586A CN 106162652 A CN106162652 A CN 106162652A
- Authority
- CN
- China
- Prior art keywords
- base station
- data
- point
- drive test
- whitening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Abstract
The invention discloses a kind of base station location localization method based on drive test data.First the present invention gathers base station signal drive test initial data, and initial data is carried out polar coordinate conversion；Secondly, the data after conversion are carried out whitening processing；Then, the data after whitening carry out k means clustering processing, determine data center's point；Finally, the central point determined carrying out polar coordinate reversion, gained coordinate information is current base station physical location.The present invention, by the research of data big to drive test, takes into full account discrete type and the dependency of data point, proposes to carry out initial data the methods such as polar coordinate conversion and whitening processing, and final application k means clustering algorithm realizes the physical location location of base station.Obtain intensity distributions and the base station signal coverage for base station signal of base station physical position coordinates are distributed important reference role.
Description
Technical field
The invention belongs to big market demand field, relate to a kind of base station location localization method based on drive test data.
Background technology
Generation information development communication technologies with Internet of Things, big data and cloud computing as representative is swift and violent, technology of Internet of things
By the continuous fusion with other new technique, accelerating to permeate to every field, accurate node locating is Internet of Things position
The key being served by.Meanwhile, " big data " have become as the focus vocabulary that current people produce and live, ubiquitous society
Can produce various data continuously with business activity, the base station signaling data that such as some city particular department gather just belongs to
One therein.It is huge for researching value based on drive test big data locking technology, especially when big data are with current
Internet of Things when blending.
Base station location localization method based on drive test data, using the drive test information data base that gathered as experimental data,
Under complicated actual environment, it is achieved the positive location of base station physical position, the information to operator of breaking away from relies on.Base station physical
On the one hand the acquisition of position, can be as the reference point of change in signal strength trend in drive test data gathering project later；Separately
On the one hand, in the algorithm of the locating base station signal cover studied later, also served as a very important reference point.
In data processing, emphasis applies k-means clustering algorithm.In actual application, clustering block is also
Do not account for the dependency of signal, cause nicety of grading not high enough, thus cause positioning precision not high enough.The present invention propose by
Carrying out k-means cluster after RSSI signal albefaction, removing the dependency between data, improve cluster centre reasonability and can
Reliability so that the positioning precision of base station has had a certain degree of raising.
Summary of the invention
The present invention, based on existing application and technical background, the deficiency processed for available data, proposes a kind of based on road
Survey the base station location localization method of data.
First the present invention gathers base station signal drive test initial data, and initial data is carried out polar coordinate conversion；Secondly, to turning
Data after changing carry out whitening processing；Then, the data after whitening carry out k-means clustering processing, determine data center's point；
Finally, the central point determined carrying out polar coordinate reversion, gained coordinate information is current base station physical location.
The invention has the beneficial effects as follows: by the research of data big to drive test, take into full account discrete type and the phase of data point
Guan Xing, proposes to carry out initial data the methods such as polar coordinate conversion and whitening processing, and final application k-means clustering algorithm realizes
The physical location location of base station.The acquisition of base station physical position coordinates covers for intensity distributions and the base station signal of base station signal
Scope is distributed important reference role.
Accompanying drawing explanation
Fig. 1 is that city drive test data gathers schematic diagram；
Fig. 2 is polar coordinate transition diagram；
Fig. 3 is clustering precision comparing result figure before and after albefaction；
Fig. 4 is base station physical location positioning Comparative result figure；
Fig. 5 is base station location positioning precision statistical result before and after albefaction.
Detailed description of the invention
Below in conjunction with accompanying drawing, the invention will be further described.
As it is shown in figure 1, use specialty road measuring device to carry out the collection of base station drive test data target area, location, wherein adopt
Collection track is according to urban road situation.Each red-label in figure represents a data sampled point, each sampled point bag
Containing movement, UNICOM, each standard data of telecommunications and WIFI data message.As a example by telecommunications 4G, contained parameter information such as following table
Shown in.
Specifically comprise the following steps that
Step one: filter out all the adopting belonging to some (LAC, CI) region from collection data according to (LAC, CI) value
Collection point.
Step 2: the point after above-mentioned screening is concentrated and found out all collection point points pair with identical RSSI value, if i-th pair
The perpendicular bisector equation of collection point is y=aix+bi, for avoiding ai, biExtreme case occurs, uses parameter transformation method to hang down
Straight bisector is converted to a polar coordinate (r, θ).As it is shown on figure 3, wherein, r is initial point o to straight line y to polar coordinate transition diagram
=aix+biDistance, θ is the angle between ray and x-axis.Point (r, θ) in space is straight corresponding in former coordinate system
Line.
Step 3: all points carry out whitening processing, the purpose of albefaction (Whitening) is removed between data relevant exactly
The redundancy brought, it is ensured that the character of data is constant, reduces dependency.The Whitening of data must is fulfilled for two conditions: one is
Between different characteristic, dependency is minimum, close to 0；Two is that all feature variances are equal.Common whitening operation has PCA Whitening
With ZCA Whitening.
PCA Whitening is to ensure that the variance of each dimension of data is 1, and ZCA Whitening is to ensure that each of data
The variance of dimension is equal.And the purposes of two kinds of Whitening is the most different, PCA Whitening is mainly used in dimensionality reduction
And decorrelation, and ZCA Whitening is mainly used in removing dependency, and keep former data as far as possible.The present invention is merely just
Want the dependency removing between data, therefore use ZCA Whitening.ZCA Whitening formula is formula (1), (2):
xZCAwhite=UxPCAwhite (2)
In above formula, xrot,iRepresent each characteristic,For zoom factor, xPCAwhiteRepresent through PCA whitening processing
Data, U represents an eigenvectors matrix.
Step 4: carry out cluster analysis, calculation base station coordinate position based on all (r, θ) coordinate points.Used K-
Means clustering algorithm mainly comprises the following steps:
1) initialize: randomly choose K seed points as cluster centre (c1,…,cK)。
2) classification of any collection point p is determined
3) the i-th class collection point set S will be belonged toiCluster centre be updated toWherein pj∈Si, inFor collection
Close SiElement number.
4) if | | ci-c′i| | < σ, σ are a certain given threshold value, then program determination；Otherwise, repeat step 2), 3) and
4), until condition meets.
Positioning result analyze: Fig. 3 show cluster centre number K from 1 to 8 change time, the clustering precision before and after albefaction.By
Fig. 3 is it can be seen that the K-means algorithm after albefaction is better than the effect before albefaction in cluster accuracy.And, along with cluster
The increase of center k value, effect becomes apparent from, this is because, in certain region, location, k value is the biggest, it is meant that by positioning area
Territory has been divided into the most subregions, and between the most adjacent subregion, the dependency of data is the biggest, after albefaction
Remove the redundancy that the dependency between data brings, be obviously improved so that the clustering precision after albefaction has had.By Fig. 3 also
It can be seen that k value is excessive or the too small raising being all unfavorable for clustering precision, with k equal to 4 as separation, k value is too small, cluster essence
Degree does not changes significantly, and k value is excessive, and clustering precision declines quickly.Therefore, the result for experiment of choosing of k value has directly
The impact connect, so the accuracy of the simplification and result in order to improve experiment, cluster centre value is positioned 4 by this experiment.Fig. 4
A (), 4 (b) are respectively base station location positioning result schematic diagram before and after albefaction.Figure identifies the tower that word is " base station physical position "
Shape labelling represents the actual physical location of base station, and another is the physical location of algorithm location.Fig. 5 is base station location before and after albefaction
Location statistical result figure.It is apparent from by Fig. 5, under different positioning precisions, clusters again after signal albefaction, reality can be significantly improved
Test positioning precision.The positioning precision after albefaction probability in 2 meters is 60%, and relatively RSS improves without the positioning precision of albefaction
About 39%；Positioning precision probability in 3 meters is about 77%, improves about 12%；And, the positioning accurate in 1 meter
Degree probability also has and the most significantly improves.
Claims (2)
1. a base station location localization method based on drive test data, it is characterised in that: first gather base station signal drive test original
Data, carry out polar coordinate conversion to initial data；Secondly, the data after conversion are carried out whitening processing；Then, after whitening
Data carry out k-means clustering processing, determine data center's point；Finally, the central point determined is carried out polar coordinate reversion, gained
Coordinate information is current base station physical location.
A kind of base station location localization method based on drive test data the most according to claim 1, it is characterised in that:
Step one: filter out all collections belonging to some (LAC, CI) region from collection data according to (LAC, CI) value
Point；
Step 2: the point after above-mentioned screening is concentrated and found out all collection point points pair with identical RSSI value, if i-th pair collection
The perpendicular bisector equation of point is y=aix+bi, use parameter transformation method perpendicular bisector is converted to polar coordinate (r,
θ)；Wherein, r is initial point o to straight line y=aix+biDistance, θ is the angle between ray and x-axis；Point (r, θ) in space is right
Straight line in Ying Yuyuan coordinate system；
Step 3: use ZCA that all points are carried out whitening processing；
Step 4: carry out K-means cluster analysis, calculation base station coordinate position, used K-based on all (r, θ) coordinate points
Means cluster analysis mainly comprises the following steps:
1) initialize: randomly choose K seed points as cluster centre (c1,…,cK)；
2) classification of any collection point p is determined
3) the i-th class collection point set S will be belonged toiCluster centre be updated toWherein pj∈Si, inFor set Si's
Element number；
4) if | | ci-c′i| | ＜ σ, σ are a certain given threshold value, then terminate；Otherwise, repeat step 2), 3) and 4), until bar
Part meets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610757586.5A CN106162652A (en) | 2016-08-29 | 2016-08-29 | A kind of base station location localization method based on drive test data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610757586.5A CN106162652A (en) | 2016-08-29 | 2016-08-29 | A kind of base station location localization method based on drive test data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106162652A true CN106162652A (en) | 2016-11-23 |
Family
ID=57345047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610757586.5A Pending CN106162652A (en) | 2016-08-29 | 2016-08-29 | A kind of base station location localization method based on drive test data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106162652A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108535684A (en) * | 2017-03-06 | 2018-09-14 | 维布络有限公司 | The method and system that the wireless transmitter spatially separated is positioned |
| CN109327902A (en) * | 2018-11-22 | 2019-02-12 | 中国联合网络通信集团有限公司 | A kind of method and apparatus of locating base station |
| CN109409176A (en) * | 2018-01-04 | 2019-03-01 | 北京星衡科技有限公司 | A kind of method and apparatus that the plot for remote sensing image is extracted |
| CN110198519A (en) * | 2019-06-26 | 2019-09-03 | 阿里巴巴集团控股有限公司 | The location estimation method and device of network access point |
| CN110691319A (en) * | 2019-09-03 | 2020-01-14 | 东南大学 | Method for realizing high-precision indoor positioning of heterogeneous equipment in self-adaption mode in use field |
| CN110881191A (en) * | 2019-11-20 | 2020-03-13 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring longitude and latitude of cell and storage medium |
| CN112839343A (en) * | 2021-01-04 | 2021-05-25 | 杭州海兴泽科信息技术有限公司 | RF terminal equipment full-coverage method facing cellular unit |
| CN114095854A (en) * | 2020-07-30 | 2022-02-25 | 中国移动通信集团广东有限公司 | Indoor distribution network interference source positioning method based on MDT data and electronic equipment |
| CN114205737A (en) * | 2021-11-23 | 2022-03-18 | 中国联合网络通信集团有限公司 | Base station cell location identification method, device and server |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102209385A (en) * | 2011-05-25 | 2011-10-05 | 厦门雅迅网络股份有限公司 | Method for calculating position of base station based on spatial outlier data mining algorithm |
| CN102802174A (en) * | 2011-05-26 | 2012-11-28 | 中国移动通信集团公司 | Drive test data acquiring method, drive test data acquiring system and drive test data acquiring device |
| CN105338498A (en) * | 2015-09-29 | 2016-02-17 | 北京航空航天大学 | Construction method for fingerprint database in WiFi indoor positioning system |
-
2016
- 2016-08-29 CN CN201610757586.5A patent/CN106162652A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102209385A (en) * | 2011-05-25 | 2011-10-05 | 厦门雅迅网络股份有限公司 | Method for calculating position of base station based on spatial outlier data mining algorithm |
| CN102802174A (en) * | 2011-05-26 | 2012-11-28 | 中国移动通信集团公司 | Drive test data acquiring method, drive test data acquiring system and drive test data acquiring device |
| CN105338498A (en) * | 2015-09-29 | 2016-02-17 | 北京航空航天大学 | Construction method for fingerprint database in WiFi indoor positioning system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108535684A (en) * | 2017-03-06 | 2018-09-14 | 维布络有限公司 | The method and system that the wireless transmitter spatially separated is positioned |
| CN108535684B (en) * | 2017-03-06 | 2021-11-05 | 维布络有限公司 | Method and system for locating spatially separated wireless transmitters |
| CN109409176A (en) * | 2018-01-04 | 2019-03-01 | 北京星衡科技有限公司 | A kind of method and apparatus that the plot for remote sensing image is extracted |
| CN109327902B (en) * | 2018-11-22 | 2021-02-23 | 中国联合网络通信集团有限公司 | Method and device for positioning base station |
| CN109327902A (en) * | 2018-11-22 | 2019-02-12 | 中国联合网络通信集团有限公司 | A kind of method and apparatus of locating base station |
| CN110198519A (en) * | 2019-06-26 | 2019-09-03 | 阿里巴巴集团控股有限公司 | The location estimation method and device of network access point |
| CN110691319A (en) * | 2019-09-03 | 2020-01-14 | 东南大学 | Method for realizing high-precision indoor positioning of heterogeneous equipment in self-adaption mode in use field |
| CN110691319B (en) * | 2019-09-03 | 2021-06-01 | 东南大学 | Method for realizing high-precision indoor positioning of heterogeneous equipment in self-adaption mode in use field |
| CN110881191A (en) * | 2019-11-20 | 2020-03-13 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring longitude and latitude of cell and storage medium |
| CN110881191B (en) * | 2019-11-20 | 2022-08-05 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring longitude and latitude of cell and storage medium |
| CN114095854A (en) * | 2020-07-30 | 2022-02-25 | 中国移动通信集团广东有限公司 | Indoor distribution network interference source positioning method based on MDT data and electronic equipment |
| CN114095854B (en) * | 2020-07-30 | 2023-08-04 | 中国移动通信集团广东有限公司 | Indoor network interference source positioning method based on MDT data and electronic equipment |
| CN112839343A (en) * | 2021-01-04 | 2021-05-25 | 杭州海兴泽科信息技术有限公司 | RF terminal equipment full-coverage method facing cellular unit |
| CN114205737A (en) * | 2021-11-23 | 2022-03-18 | 中国联合网络通信集团有限公司 | Base station cell location identification method, device and server |
| CN114205737B (en) * | 2021-11-23 | 2023-07-07 | 中国联合网络通信集团有限公司 | Base station cell position identification method, device and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106162652A (en) | A kind of base station location localization method based on drive test data | |
| Ranjan et al. | Asap: Adaptive structure aware pooling for learning hierarchical graph representations | |
| CN109640269B (en) | Fingerprint positioning method based on CSI and time domain fusion algorithm | |
| CN108537775A (en) | A kind of cancer cell tracking based on deep learning detection | |
| CN107679558A (en) | A kind of user trajectory method for measuring similarity based on metric learning | |
| CN106599915B (en) | A kind of vehicle-mounted laser point cloud classifications method | |
| CN108806301B (en) | Automatic identification method for bus information | |
| CN103077407A (en) | Car logo positioning and recognition method and car logo positioning and recognition system | |
| US11255678B2 (en) | Classifying entities in digital maps using discrete non-trace positioning data | |
| CN115374375B (en) | Track clustering method, system and storage medium based on deep learning | |
| CN112434566B (en) | Passenger flow statistics method and device, electronic equipment and storage medium | |
| CN111008574A (en) | Key person track analysis method based on body shape recognition technology | |
| EP4105600A2 (en) | Method for automatically producing map data, related apparatus and computer program product | |
| CN112651266A (en) | Pedestrian detection method and device | |
| CN108182218A (en) | A kind of video character recognition method, system and electronic equipment based on GIS-Geographic Information System | |
| Makris et al. | A comparison of trajectory compression algorithms over AIS data | |
| CN110895879A (en) | Method and device for detecting co-running vehicle, storage medium and electronic device | |
| Eum et al. | Vehicle detection from airborne LiDAR point clouds based on a decision tree algorithm with horizontal and vertical features | |
| CN113128584B (en) | Mode-level unsupervised sorting method of multifunctional radar pulse sequence | |
| CN103235791A (en) | Optimizing positioning method for fingerprint-matching based on rank order | |
| CN110909804B (en) | Method, device, server and storage medium for detecting abnormal data of base station | |
| CN113553239B (en) | Abnormal data detection method and related device | |
| CN114613124B (en) | Traffic information processing method, device, terminal and computer readable storage medium | |
| Zhao et al. | One‐shot video‐based person re‐identification with variance subsampling algorithm | |
| Zhang et al. | Hierarchical Image Retrieval Method Based on Bag-of-Visual-Word and Eight-point Algorithm with Feature Clouds for Visual Indoor Positioning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20200407 |
|
| AD01 | Patent right deemed abandoned |